Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    entities related to function calls and their parameters in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code or data references

    np_acts-logits-general · gemini-2.0-flash

    ref or reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <?>
    -0.54
    TintMode
    -0.51
    drawSprites
    -0.50
    ItemBackground
    -0.47
     expectancy
    -0.47
    دانشنامهٔ
    -0.46
     Roskov
    -0.45
     nigra
    -0.43
     mediocrity
    -0.42
    anthrene
    -0.42
    POSITIVE LOGITS
     ref
    1.59
    ref
    1.42
    Ref
    1.04
     Ref
    1.03
     refs
    1.01
    REF
    0.96
     reference
    0.90
    Refs
    0.90
     REF
    0.88
    refs
    0.86
    Act Density 0.166%

    No Known Activations